List: Experiments | Curated by Ala Falaki, PhD | Medium

Ala Falaki, PhD

Jul 20, 2023

8 stories

Experiments

In

Towards AI

by

Ala Falaki, PhD

Fine-Tune BART for Translation on WMT16 Dataset (and Train new Tokenizer)

BART is a well-known summarization model. Also, it can do the translation task with the appropriate tokenizer for the target language.

Mar 13, 2023

Fine-Tune BART for Translation on WMT16 Dataset (and Train new Tokenizer)

Mar 13, 2023

In

Towards AI

by

Ala Falaki, PhD

CompressedBART: Fine-Tuning for Summarization through Latent Space Compression (Paper…

Paper title: A Robust Approach to Fine-tune Pre-trained Transformer-based Models for Text Summarization through Latent Space Compression.

Apr 7, 2023

A spring between two hands being compressed.

Apr 7, 2023

In

Towards AI

by

Ala Falaki, PhD

How To Do Effective Paraphrasing Using Huggingface and Diverse Beam Search? (T5, Pegasus,…)

The available paraphrasing models usually don’t perform as advertised. However, some techniques can help you easily get the most out of…

Sep 12, 2022

How To Do Effective Paraphrasing Using Huggingface and Diverse Beam Search? (T5, Pegasus,…)

Sep 12, 2022

In

Towards AI

by

Ala Falaki, PhD

Attention Visualizer Package: Showcase Highest Scored Words Using RoBERTa Model

This library lets you easily see which words contribute the most in terms of self-attention score in each layer and head to the output…

Jan 24, 2022

Attention Visualizer Package: Showcase Highest Scored Words Using RoBERTa Model

Jan 24, 2022

In

Towards AI

by

Ala Falaki, PhD

Let AI Write Stories for You!! (Using GPT-J)

The family of GPT models keeps improving the quality of the generated text to the point that they are now being used to write blog posts.

Dec 15, 2021

Let AI Write Stories for You!! (Using GPT-J)

Dec 15, 2021

Ala Falaki, PhD

Is it possible to do Sentiment Analysis on unlabeled data using BERT? (Feat. Vader) [Experiment]

Supervised learning algorithms like Artificial Neural Networks (ANN) basically rely on examples to learn from. Each instance should be a…

Apr 23, 2021

Is it possible to do Sentiment Analysis on unlabeled data using BERT? (Feat. Vader) [Experiment]

Apr 23, 2021

In

Towards AI

by

Ala Falaki, PhD

How much DEEP learning do we need?

The growing trend of large pre-trained networks is worrying. It could send the message that Deep Learning is not for everyone.

Aug 4, 2021

How much DEEP learning do we need?

Aug 4, 2021

In

Towards AI

by

Ala Falaki, PhD

Is it possible to do Text Classification on unlabeled data? (Feat. Zero-Shot Classification)

In this piece we will explore the zero-shot classification method for sentiment analysis using the Huggingface library.

Aug 30, 2021

Is it possible to do Text Classification on unlabeled data? (Feat. Zero-Shot Classification)

Aug 30, 2021

Ala Falaki, PhD

Ala Falaki, PhD

Technical Editor @ Towards AI - Write about NLP here. Let's talk on Twitter! https://nlpiation.github.io/

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams